检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Liao, Haisu Ren, Zhongliang Wang, Yidi Wu, Xinyu Gao, Fei Southern University of Science and Technology Shenzhen518005 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China

ISBN: (纸本)9781665481090

Harvesting energy from the human body to extend the operational time for low-power has gained significant attention. Recently, researchers have focused on biomechanical energy harvesting from human feet while walking. This paper presents an optimization of the cam profile for a piezoelectric-based sole energy harvester designed to be worn on the bottom of shoes to power electronic devices. Specifically, cams with linear polynomial and exponential functions were designed to actuate the piezoelectric transducers (PZTs). Force analysis revealed that the exponential function cam induces more significant deformation in the PZTs than the linear polynomial cam. Preliminary tests on a healthy subject validated this design, showing that the exponential function cam produced an average output power of 0.16mW at a walking speed of 5.5 km/h, indicating a 78% improvement over the linear polynomial cam. Moreover, the optimization rate increased with the growing walking speed. © 2024 IEEE.

关键词： Piezoelectric transducers

来源：评论

学校读者我要写书评

暂无评论

Class-specific Prompts in Vision Transformer for Continual Learning of New Diseases

Class-specific Prompts in Vision Transformer for Continual L...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Defeng Zhao Zejun Ye Wei-Shi Zheng Ruixuan Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE China Department of Network Intelligence Peng Cheng Laboratory Shenzhen China

Current intelligent diagnosis systems are often trained to diagnose a small number of diseases and lack the ability of continually learning new disease knowledge. To have such continual learning ability, the deployed intelligent system needs to be continually updated based on training data of only new diseases, without accessing old data of previously learned diseases due to privacy concerns and challenges in data sharing across medical centers. In this study, a novel and effective prompt learning strategy is proposed to help a pretrained and fixed Vision Transformer (ViT) continually learn new diseases. In particular, a set of unique prompts for each disease are effectively learned such that discriminative disease features can be well extracted from the fixed ViT under the instructions of prompts during feature extraction, even though the ViT feature extractor is pretrained in the natural image domain. Extensive empirical evaluations on two medical image datasets and one natural image dataset demonstrate the superior performance of the proposed method. The source code is available at https://***/zhaoedf/CSPrompt.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization

arXiv

引用

arXiv 2024年

作者： Du, Jia-Run Lin, Kun-Yu Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University China

To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for unseen categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposallevel objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the categoryagnostic dynamic information of actions. Besides, we introduce a Static- Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively. The code is available at https://***/Run542968/GAP. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Pallas: Optimizing Userspace TCP Stack for Short-Lived Connections

Pallas: Optimizing Userspace TCP Stack for Short-Lived Conne...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Haiqiang Lin Wenxin Li Wenyu Qu Tianjin Key Laboratory of Advanced Networking (TANK) College of Intelligence and Computing Tianjin University China

Short-lived TCP connections are important for modern Internet applications and call for efficient network stack support. Traditional Linux TCP stack is inefficient because of the inherent kernel overheads like context switching and memory copy. A promising alternative, called user-level TCP stack, is thus becoming attractive in this context. However, existing user-level stacks mainly focus on scalability issues when handling shortlived connections and fall short in optimizing request-response latency. To fill this gap, this paper presents Pallas, a built-in packet scheduler in the user-space mTCP stack, to prioritize the transmissions of short connections over long connections to reduce the request-response latency. Pallas schedules at packetlevel first to complete 1-packet short connections as quickly as possible and then smoothly switches to connection-level to defer the transmissions of long connections. We have implemented a Pallas prototype and evaluated it on a 4-core machine. The results show that Pallas-enhanced mTCP delivers significant performance. For example, it speeds up the overall request response time of mTCP by 1.49 times.

关键词： Schedules Scheduling algorithms Scalability Linux Prototypes Switches Scheduling

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Teacher-Student Framework for Real-time Video Inference in Multi-User Heterogeneous MEC Networks

An Adaptive Teacher-Student Framework for Real-time Video In...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yuan Lu Shuxin Ge Weixu Wang Xiaobo Zhou Tie Qiu Tianjin Key Laboratory of Advanced Networking College of Intelligence and Computing Tianjin University Tianjin China

Teacher-student learning has emerged as a promising framework for real-time video inference on mobile devices in multi-access edge computing (MEC) networks, where heavyweight teacher models are deployed on edge servers, and lightweight student models distilled from teacher models are deployed on mobile devices. To deal with data drift and maintain the inference accuracy, the student model has to be updated periodically with the help of the teacher model through a training process. Different training configurations, such as training epochs and frozen layers, lead to different accuracy improvements with different resource requirements. However, in multi-user heterogeneous MEC networks, due to resource heterogeneity and limited computing resources of edge servers, it is quite challenging to update all the student models simultaneously to achieve high inference accuracy. To address this problem, in this paper, we propose an adaptive teacher-student framework in multi-user heterogeneous MEC networks. The key idea is to adaptively make optimal updating decisions (i.e., offloading decision and configuration selection decision) for each user, where the available resources of edge servers and network conditions are taken into account. First, we model the teacher-student collaborative video inference problem as an optimization problem with the aim of maximizing the average inference accuracy. Then, we propose an evolutionary deep reinforcement learning algorithm, CEM-MASAC, to solve this problem. Finally, trace-driven simulations employing real-world bandwidth traces demonstrate the superiority of our algorithm compared to the baseline methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WSTrack: A Wi-Fi and Sound Fusion System for Device-free Human Tracking

WSTrack: A Wi-Fi and Sound Fusion System for Device-free Hum...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Yichen Tian Yunliang Wang Ruikai Zheng Xiulong Liu Xinyu Tong Keqiu Li College of Intelligence and Computing Tianjin University China Tianjin Key Laboratory of Advanced Networking (TANK)

The voice assistants benefit from the ability to localize users, especially, we can analyze the user’s habits from the historical trajectory to provide better services. However, current voice localization method requires the user to actively issue voice commands, which makes voice assistants unable to track silent users most of the time. This paper presents WSTrack, a Wi-Fi and Sound fusion tracking system for device-free human. In particular, current voice assistants naturally support both Wi-Fi and acoustic functions. Accordingly, we are able to build up the multi-modal prototype with just voice assistants and Wi-Fi routers. To track the movement of silent users, our insights are as follows: (1) the voice assistants can hear the sound of the user’s pace, and then extract which direction the user is in; (2) we can extract the user’s velocity from the Wi-Fi signal. By fusing multi-modal information, we are able to track users with a single voice assistant and Wi-Fi router. Our implementation and evaluation on commodity devices demonstrate that WSTrack achieves better performance than current systems, where the median tracking error is 0.37m.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Residual Classifier for Class Incremental Learning

Dynamic Residual Classifier for Class Incremental Learning

引用

International Conference on Computer Vision (ICCV)

作者： Xiuwei Chen Xiaobin Chang School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Swarm: A High-Performance Asynchronous BFT Protocol Adapted to High Network Delay

Swarm: A High-Performance Asynchronous BFT Protocol Adapted ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Jianyu Han Xiulong Liu Keqiu Li College of Intelligence and Computing Tianjin University China Tianjin Key Laboratory of Advanced Networking (TANK)

Recently, asynchronous byzantine fault tolerance (BFT) consensus has made progress in linearized communication complexity, allowing nodes to broadcast a small number of transactions at their own pace in networks with variable bandwidth. However, this means that network propagation delay poses a more severe bottleneck to the system compared to transmission delay affected by block size and bandwidth. Particularly in networks with high propagation delays, nodes need to wait more for messages to propagate through the network, which severely hinders system performance. We propose Swarm, an asynchronous BFT protocol that is suitable for networks with tight bandwidth and propagation delay. The new protocol structure supports highly concurrent propagation-delay-intensive and propagationdelay-tolerant stages by separating the control and data layers and ensures that nodes achieve an ordered and consistent log for parallel blocks. We also design a group broadcasting strategy that allows nodes to not broadcast proposals from other nodes without compromising safety and liveness while reducing communication cost. Importantly, our work is orthogonal to existing improvements based on communication complexity and bandwidth and does not sacrifice existing results. We built a complete system prototype and conducted a thorough evaluation. The results show that Swarm performs better in networks with higher propagation delays, achieving 2-5x TPS and reducing latency by 50% compared to existing asynchronous protocols for different scales.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secur-Fi: A Secure Wireless Sensing System Based on Commercial Wi-Fi Devices

Secur-Fi: A Secure Wireless Sensing System Based on Commerci...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Xuanqi Meng Jiarun Zhou Xiulong Liu Xinyu Tong Wenyu Qu Jianrong Wang College of Intelligence and Computing Tianjin University China Tianjin Key Laboratory of Advanced Networking (TANK)

Wi-Fi sensing technology plays an important role in numerous IoT applications such as virtual reality, smart homes and elder healthcare. The basic principle is to extract physical features from the Wi-Fi signals to depict the user’s locations or behaviors. However, current research focuses more on improving the sensing accuracy but neglects the security concerns. Specifically, current Wi-Fi router usually transmits a strong signal, so that we can access the Internet even through the wall. Accordingly, the outdoor adversaries are able to eavesdrop on this strong Wi-Fi signal, and infer the behavior of indoor users in a non-intrusive way, while the indoor users are unaware of this eavesdropping. To prevent outside eavesdropping, we propose Secur-Fi, a secure Wi-Fi sensing system. Our system meets the following two requirements: (1) we can generate fraud signals to block outside unauthorized Wi-Fi sensing; (2) we can recover the signal, and enable authorized Wi-Fi sensing. We implement the proposed system on commercial Wi-Fi devices and conduct experiments in three applications including passive tracking, behavior recognition, and breath detection. The experiment results show that our proposed approaches can reduce the accuracy of unauthorized sensing by 130% (passive tracking), 72% (behavior recognition), 86% (breath detection).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Consistent Prompting for Rehearsal-Free Continual Learning

arXiv

引用

arXiv 2024年

作者： Gao, Zhanxin Cen, Jun Chang, Xiaobin School of Artificial Intelligence Sun Yat-Sen University China Cheng Kar-Shun Robotics Institute The Hong Kong University of Science and Technology Hong Kong Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts and classifiers efficiently. Existing prompt-based methods are inconsistent between training and testing, limiting their effectiveness. Two types of inconsistency are revealed. Test predictions are made from all classifiers while training only focuses on the current task classifier without holistic alignment, leading to Classifier inconsistency. Prompt inconsistency indicates that the prompt selected during testing may not correspond to the one associated with this task during training. In this paper, we propose a novel prompt-based method, Consistent Prompting (CPrompt), for more aligned training and testing. Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning. In addition, prompt consistency learning is proposed to enhance prediction robustness and boost prompt selection accuracy. Our Consistent Prompting surpasses its prompt-based counterparts and achieves state-of-the-art performance on multiple continual learning benchmarks. Detailed analysis shows that improvements come from more consistent training and testing. Our code is available at https://***/Zhanxin-Gao/CPrompt. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：